• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.2
• /
• pp.72-81
• /
• 2023

This research proposes a novel approach to tackle the challenge of categorizing unstructured customer complaints in the automotive industry. The goal is to identify potential vehicle defects based on the findings of our algorithm, which can assist automakers in mitigating significant losses and reputational damage caused by mass claims. To achieve this goal, our model uses the Word2Vec method to analyze large volumes of unstructured customer complaint data from the National Highway Traffic Safety Administration (NHTSA). By developing a score dictionary for eight pre-selected criteria, our algorithm can efficiently categorize complaints and detect potential vehicle defects. By calculating the score of each complaint, our algorithm can identify patterns and correlations that can indicate potential defects in the vehicle. One of the key benefits of this approach is its ability to handle a large volume of unstructured data, which can be challenging for traditional methods. By using machine learning techniques, we can extract meaningful insights from customer complaints, which can help automakers prioritize and address potential defects before they become widespread issues. In conclusion, this research provides a promising approach to categorize unstructured customer complaints in the automotive industry and identify potential vehicle defects. By leveraging the power of machine learning, we can help automakers improve the quality of their products and enhance customer satisfaction. Further studies can build upon this approach to explore other potential applications and expand its scope to other industries.

• The Journal of Bigdata
• /
• v.7 no.1
• /
• pp.37-47
• /
• 2022

Autonomous delivery operation data is the key to driving a paradigm shift for last-mile delivery in the Corona era. To bridge the technological gap between domestic autonomous delivery robots and overseas technology-leading countries, large-scale data collection and verification that can be used for artificial intelligence training is required as the top priority. Therefore, overseas technology-leading countries are contributing to verification and technological development by opening AI training data in public data that anyone can use. In this paper, 326 objects were collected to trainn autonomous delivery robots, and artificial intelligence models such as Mask r-CNN and Yolo v3 were trained and verified. In addition, the two models were compared based on comparison and the elements required for future autonomous delivery robot research were considered.

• Convergence Security Journal
• /
• v.22 no.2
• /
• pp.9-19
• /
• 2022

As the expansion of digital transformation, we are more exposed to the threat of cyber attacks, and many institution or company is operating a signature-based intrusion prevention system at the forefront of the network to prevent the inflow of attacks. However, in order to provide appropriate services to the related ICT system, strict blocking rules cannot be applied, causing many false events and lowering operational efficiency. Therefore, many research projects using artificial intelligence are being performed to improve attack detection accuracy. Most researches were performed using a specific research data set which cannot be seen in real network, so it was impossible to use in the actual system. In this paper, we propose a technique for classifying major attack keywords in the security event log collected from the actual system, assigning a weight to each key keyword, and then performing a similarity check using TF-IDF to determine whether an actual attack has occurred.

• Smart Structures and Systems
• /
• v.31 no.1
• /
• pp.57-68
• /
• 2023

Bridge hangers, such as those in suspension and cable-stayed bridges, suffer from cumulative fatigue damage caused by dynamic loads (e.g., cyclic traffic and wind loads) in their service condition. Thus, the identification of damage to hangers is important in preserving the service life of the bridge structure. This study develops a new method for condition assessment of bridge hangers. The tension force of the bridge and the damages in the element level can be identified using the Bayesian optimization method. To improve the number of observed data, the additional mass method is combined the Bayesian optimization method. Numerical studies are presented to verify the accuracy and efficiency of the proposed method. The influence of different acquisition functions, which include expected improvement (EI), probability-of-improvement (PI), lower confidence bound (LCB), and expected improvement per second (EIPC), on the identification of damage to the bridge hanger is studied. Results show that the errors identified by the EI acquisition function are smaller than those identified by the other acquisition functions. The identification of the damage to the bridge hanger with various types of boundary conditions and different levels of measurement noise are also studied. Results show that both the severity of the damage and the tension force can be identified via the proposed method, thereby verifying the robustness of the proposed method. Compared to the genetic algorithm (GA), particle swarm optimization (PSO), and nonlinear least-square method (NLS), the Bayesian optimization (BO) performs best in identifying the structural damage and tension force.

• Journal of Korean Society for Quality Management
• /
• v.51 no.2
• /
• pp.155-170
• /
• 2023

Purpose: Nowadays, the risk assessment system is widely used in many industrial and public areas to reduce the possible risks. The system is used to determine the priorities of the government quality assurance works in Defense Agency for Technology and Quality. However, as the risk assessment system is used for other purposes, there are some items that need improvement, and in this study, we propose improvement plans by benchmarking the risk assessment systems of other institutions. Methods: In this paper, first, the procedures of risk assessment system used in many industrial sites were reviewed, and how each institution specialized and applied the system. Afterwards, by benchmarking various risk assessment systems, an improvement plan on how to operate the risk assessment system in the case of government quality assurance for centrally procured military supplies was presented, and practical application cases were presented to prove the usefulness of the improvement plan. Results: The proposed risk assessment system differs from the existing system in five major aspects. First, inputs, outputs, and key performance indicators were specified from the systematic point of view. Second, risk analysis was analyzed in four dimensions: probability of occurrence, impact, detection difficulty. Third, risk mitigation measures were classified, control, transfer, and sharing. Fourth, the risk mitigation measures were realized through document verification, product verification, process verification, and quality system evaluation. Finally, risk mitigation measures were implemented and the effectiveness of the risk mitigation measures was evaluated through effectiveness evaluation. Conclusions: In order for the risk assessment procedure proposed in this study to be applied to actual work, it is necessary to obtain the consent of the person involved in the work due to the increased time for risk identification and preparation of the government quality assurance log, and a change in the information system that performs the actual work is required. Therefore, the authors of this study plan to actively perform internal seminar presentations and work improvement suggestions to apply these research outputs to actual work.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.256-257
• /
• 2022

In this paper, we introduce a method of extracting three-dimensional feature points through the movement of a single mobile device. Using a monocular camera, a 2D image is acquired according to the camera movement and a baseline is estimated. Perform stereo matching based on feature points. A feature point and a descriptor are acquired, and the feature point is matched. Using the matched feature points, the disparity is calculated and a depth value is generated. The 3D feature point is updated according to the camera movement. Finally, the feature point is reset at the time of scene change by using scene change detection. Through the above process, an average of 73.5% of additional storage space can be secured in the key point database. By applying the algorithm proposed to the depth ground truth value of the TUM Dataset and the RGB image, it was confirmed that the\re was an average distance difference of 26.88mm compared with the 3D feature point result.

• Journal of Advanced Navigation Technology
• /
• v.27 no.5
• /
• pp.540-545
• /
• 2023

AESA radar is able to instantaneously and adaptively position and control the beam, and this enables to have interleaved mode in modern airborne AESA radar which can maximize situational awareness capability. Interleaved mode provides two or more modes simultaneously, such as Air to Air mode and Sea Surface mode by time sharing technique. In this interleaved mode, performance degradation is inevitable, compared with single mode operation, and effective resource allocation is the key component for the success of interleaved mode. In this paper, we identified performance evaluation items for each mode to analyze interleaved mode performance and proposed effective resource allocation methodology to achieve graceful performance degradation of each mode, focusing on detection range. We also proposed beam scheduling techniques for interleaved mode.

• Convergence Security Journal
• /
• v.24 no.2
• /
• pp.9-17
• /
• 2024

This paper examines the security threats to enterprise Generative Artificial Intelligence systems and proposes countermeasures. As AI systems handle vast amounts of data to gain a competitive edge, security threats targeting AI systems are rapidly increasing. Since AI security threats have distinct characteristics compared to traditional human-oriented cybersecurity threats, establishing an AI-specific response system is urgent. This study analyzes the importance of AI system security, identifies key threat factors, and suggests technical and managerial countermeasures. Firstly, it proposes strengthening the security of IT infrastructure where AI systems operate and enhancing AI model robustness by utilizing defensive techniques such as adversarial learning and model quantization. Additionally, it presents an AI security system design that detects anomalies in AI query-response processes to identify insider threats. Furthermore, it emphasizes the establishment of change control and audit frameworks to prevent AI model leakage by adopting the cyber kill chain concept. As AI technology evolves rapidly, by focusing on AI model and data security, insider threat detection, and professional workforce development, companies can improve their digital competitiveness through secure and reliable AI utilization.

• International Journal of Stem Cells
• /
• v.16 no.2
• /
• pp.135-144
• /
• 2023

Background and Objectives: Melanocyte (MC), derived from neural crest stem cell (NCSC), are involved in the production of melanin. The mechanism by which NCSC differentiates to MC remains unclear. N6-methyladenosine (m6A) modification was applied to discuss the potential mechanism. Methods and Results: NCSCs were isolated from hair follicles of rats, and were obtained for differentiation. Cell viability, tyrosinase secretion and activity, and transcription factors were combined to evaluated the MC differentiation. RT-qPCR was applied to determine mRNA levels, and western blot were used for protein expression detection. Total m6A level was measured using methylated RNA immunoprecipitation (MeRIP) assay, and RNA immunoprecipitation was used to access the protein binding relationship. In current work, NCSCs were successfully differentiated into MCs. Fat mass and obesity associated gene (FTO) was aberrant downregulated in MCs, and elevated FTO suppressed the differentiation progress of NCSCs into MCs. Furthermore, microphthalmia-associated transcription factor (Mitf), a key gene involved in MC synthesis, was enriched by FTO in a m6A modification manner and degraded by FTO. Meanwhile, the suppression functions of FTO in the differentiation of NCSCs into MCs were reversed by elevated Mitf. Conclusions: In short, FTO suppressed the differentiating ability of hair follicle-derived NCSCs into MCs by m6A modifying Mitf.

• Journal of Korean Society for Quality Management
• /
• v.51 no.4
• /
• pp.515-530
• /
• 2023

Purpose : This research aims to develop a data-driven inspection policy for radio stations utilizing the KS Q ISO 2859-1 sampling method, addressing potential regulatory relaxations and impending management challenges. Methods : Using radio station inspection big data from the past six years, we established a simulation model to evaluate the current policy. A new inspection sampling policy framework was designed based on the KS Q ISO 2859-1 method. The study compares the performance of the current and proposed inspection systems, offering insights for an improved inspection strategy. Results : This study introduced a simulation model for inspection system based on the KS Q ISO 2859-1 sampling method. Through various experimental designs, key performance indicators such as non-detection rate and sample proportion were derived, providing foundational data for the new inspection policy. Conclusion : Using big data from radio station inspections, we evaluated current inspection systems and quantitatively compared a new system across diverse scenarios. Our simulation model effectively verified the feasibility and efficiency of the proposed framework. For practical implementation, essential factors such as lot size, inspection cycle, and AQL standards need precise definition and consideration. Enhancing radio station inspections requires a policy-driven approach that factors in socio-economic impacts and solicits feedback from industry participants. Future study should also explore various perspectives related to legislative, institutional, and operational aspects of inspection organizations.